Saved in:
Bibliographic Details
Main Authors: Yu, Ziqing, Tao, Yuhui, Huo, Jiayu, Pan, Lei, Xiao, Zilong, Chen, Juecheng, Li, Xiao, Li, Jianxuan, Zhou, You, Li, Zhixing, Wang, Cong, Zhang, Beijian, Chen, Chen, Lu, Hongyang, Patlatzoglou, Konstantinos, Kramer, Daniel B., Waks, Jonathan W., Su, Yangang, Ng, Fu Siong, Wang, Shuo, Liang, Yixiu, Ge, Junbo
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2605.25446
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913161230155776
author Yu, Ziqing
Tao, Yuhui
Huo, Jiayu
Pan, Lei
Xiao, Zilong
Chen, Juecheng
Li, Xiao
Li, Jianxuan
Zhou, You
Li, Zhixing
Wang, Cong
Zhang, Beijian
Chen, Chen
Lu, Hongyang
Patlatzoglou, Konstantinos
Kramer, Daniel B.
Waks, Jonathan W.
Su, Yangang
Ng, Fu Siong
Wang, Shuo
Liang, Yixiu
Ge, Junbo
author_facet Yu, Ziqing
Tao, Yuhui
Huo, Jiayu
Pan, Lei
Xiao, Zilong
Chen, Juecheng
Li, Xiao
Li, Jianxuan
Zhou, You
Li, Zhixing
Wang, Cong
Zhang, Beijian
Chen, Chen
Lu, Hongyang
Patlatzoglou, Konstantinos
Kramer, Daniel B.
Waks, Jonathan W.
Su, Yangang
Ng, Fu Siong
Wang, Shuo
Liang, Yixiu
Ge, Junbo
contents Electrocardiography (ECG) is central to cardiovascular care, but conventional AI models are often restricted to common arrhythmias and may generalize poorly across populations or clinically subtle diseases. We developed ECG Contrastive Language-Image Pre-training (ECGCLIP), a signal-language contrastive learning framework that aligns ECG waveforms with expert diagnostic reports. ECGCLIP was pre-trained on 2,837,962 ECG studies from 1,324,856 patients and evaluated on a held-out internal test set plus nine independent external cohorts comprising about 1.5 million ECGs. Evaluation covered 89 downstream tasks, including 45 ECG diagnoses, 39 echocardiographic targets, and 5 rare cardiac diseases, using PRAUC as the primary metric. ECGCLIP consistently improved performance over random initialization and Merl-R18 baselines. On the internal test set, ECGCLIP-R34 achieved strong performance for atrial fibrillation (PRAUC 0.900) and ST-segment elevation myocardial infarction (PRAUC 0.383), with robust generalization across all external cohorts. It also improved low-prevalence and diagnostically elusive diseases, including Ebstein anomaly, constrictive pericarditis, dextrocardia, and cardiac amyloidosis, with internal PRAUC values of 0.253, 0.175, 0.121, and 0.201, respectively. ECGCLIP was data efficient, matching or exceeding full-dataset baseline performance with only 10% of training data. Feature visualization and saliency analysis suggested clinically meaningful representations aligned with established electrocardiographic criteria. These findings indicate that large-scale ECG-report contrastive pre-training can expand routine ECG interpretation beyond common arrhythmias toward broad cardiovascular assessment and opportunistic screening of echocardiographic and rare conditions.
format Preprint
id arxiv_https___arxiv_org_abs_2605_25446
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle A Signal-Language Foundation Model for Broad-Spectrum Cardiovascular Assessment from Routine Electrocardiography
Yu, Ziqing
Tao, Yuhui
Huo, Jiayu
Pan, Lei
Xiao, Zilong
Chen, Juecheng
Li, Xiao
Li, Jianxuan
Zhou, You
Li, Zhixing
Wang, Cong
Zhang, Beijian
Chen, Chen
Lu, Hongyang
Patlatzoglou, Konstantinos
Kramer, Daniel B.
Waks, Jonathan W.
Su, Yangang
Ng, Fu Siong
Wang, Shuo
Liang, Yixiu
Ge, Junbo
Artificial Intelligence
Machine Learning
Electrocardiography (ECG) is central to cardiovascular care, but conventional AI models are often restricted to common arrhythmias and may generalize poorly across populations or clinically subtle diseases. We developed ECG Contrastive Language-Image Pre-training (ECGCLIP), a signal-language contrastive learning framework that aligns ECG waveforms with expert diagnostic reports. ECGCLIP was pre-trained on 2,837,962 ECG studies from 1,324,856 patients and evaluated on a held-out internal test set plus nine independent external cohorts comprising about 1.5 million ECGs. Evaluation covered 89 downstream tasks, including 45 ECG diagnoses, 39 echocardiographic targets, and 5 rare cardiac diseases, using PRAUC as the primary metric. ECGCLIP consistently improved performance over random initialization and Merl-R18 baselines. On the internal test set, ECGCLIP-R34 achieved strong performance for atrial fibrillation (PRAUC 0.900) and ST-segment elevation myocardial infarction (PRAUC 0.383), with robust generalization across all external cohorts. It also improved low-prevalence and diagnostically elusive diseases, including Ebstein anomaly, constrictive pericarditis, dextrocardia, and cardiac amyloidosis, with internal PRAUC values of 0.253, 0.175, 0.121, and 0.201, respectively. ECGCLIP was data efficient, matching or exceeding full-dataset baseline performance with only 10% of training data. Feature visualization and saliency analysis suggested clinically meaningful representations aligned with established electrocardiographic criteria. These findings indicate that large-scale ECG-report contrastive pre-training can expand routine ECG interpretation beyond common arrhythmias toward broad cardiovascular assessment and opportunistic screening of echocardiographic and rare conditions.
title A Signal-Language Foundation Model for Broad-Spectrum Cardiovascular Assessment from Routine Electrocardiography
topic Artificial Intelligence
Machine Learning
url https://arxiv.org/abs/2605.25446